Home
Projects
Resources
Alternatives
Blog
Sign In
ConvNetSharp Versions
Save
Deep Learning in C#
Overview
Versions
Reviews
Resources
0.4.14
4 years ago
Update to .NET Core 3.1 / .NET Standard 2.1
Cuda 10.0 / cuDNN cuDNN v7.6.4
0.4.12
4 years ago
Remove unused regularization parameters (#137)
Managed Cuda 9 1 (#136)
Fix Dropout exception (#133)
v0.4.11
5 years ago
Bug fixes:
Wrong gradient computation in Flow when batch size > 1 #128
New features:
Matrix multiplication / Transpose / RNN demo #129
v0.4.10
6 years ago
Bug fixes:
GPU memory improvements #121
Make Shape simplier => always 4 dimensions #120
Dropout is wrong in Flow #118
v0.4.9
6 years ago
Fix missing kernels
v0.4.7
6 years ago
Crash in backward pass of Dropout in GPU (#90)
DropoutLayer Missing Method Exception (#92)
Add Dropout in Core and Flow #96
Assigment op (#97 )
Sqrt op (#98 )
Power op (#99)
Adam optimizer (#100 )
v0.4.5_bis
6 years ago
Bug fix: o Missing kernels in resources (#85 )
v0.4.4
6 years ago
Enforce use of BuilderInstance rather than 'new Volume'
Fix missing initialisation in regression layer
netstandard 2.0
v0.4.3
6 years ago
DropOut layer #42
Leaky ReLU #12
Save and Load Serialization #67
Some fixes for dropout layers #71
Fix regression layer loss computation
v0.4.2
6 years ago
Fix several issues in ConvNetSharp.Flow
Some perf improvements
« Previous
Next »
Home
Projects
Resources
Alternatives
Blog
Sign In
Sign In to OSA
I agree with
Terms of Service
and
Privacy Policy
Sign In with Github